科研项目同行评议专家学术专长匹配方法

doi:10.11772/j.issn.1001-9081.2020101564

计算机应用 ›› 2021, Vol. 41 ›› Issue (8): 2418-2426.DOI: 10.11772/j.issn.1001-9081.2020101564

所属专题：第八届CCF大数据学术会议（CCF Bigdata 2020）

• 第八届CCF大数据学术会议 • 上一篇下一篇

科研项目同行评议专家学术专长匹配方法

王梓森^1,2, 梁英¹, 刘政君^1,2, 谢小杰^1,2, 张伟^1,2, 史红周¹

1. 中国科学院计算技术研究所, 北京 100190;
2. 中国科学院大学计算机科学与技术学院, 北京 100049

收稿日期:2020-10-10 修回日期:2020-12-03 出版日期:2021-08-10 发布日期:2021-01-27
通讯作者: 梁英
作者简介:王梓森(1998-),男,山东烟台人,硕士研究生,CCF会员,主要研究方向:数据挖掘、机器学习;梁英(1962-),女,北京人,高级工程师,硕士,CCF高级会员,主要研究方向:数据挖掘、大数据处理、普适计算;刘政君(1997-),男,山东聊城人,硕士研究生,CCF会员,主要研究方向:数据挖掘;谢小杰(1996-),男,湖南衡阳人,硕士研究生,CCF会员,主要研究方向:数据挖掘;张伟(1993-),男,安徽六安人,硕士研究生,主要研究方向:数据挖掘;史红周(1971-),男,陕西梅县人,高级工程师,博士,CCF会员,主要研究方向:物端协同计算、物联网安全、大数据。
基金资助:
国家重点研发计划项目（2018YFB1004700）。

Matching method for academic expertise of research project peer review experts

WANG Zisen^1,2, LIANG Ying¹, LIU Zhengjun^1,2, XIE Xiaojie^1,2, ZHANG Wei^1,2, SHI Hongzhou¹

1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;
2. College of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-10-10 Revised:2020-12-03 Online:2021-08-10 Published:2021-01-27
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2018YFB1004700).

摘要/Abstract

摘要： 现有的评审专家推荐过程通常依赖于人工匹配，在进行专家推荐时不能充分捕捉评审项目所属学科与专家研究兴趣之间的语义关联，导致专家推荐的精确性较低。为解决这个问题，提出了一种科研项目同行评议专家学术专长匹配方法。该方法构建学术网络以建立学术实体联系，并设计元路径捕捉学术网络中不同节点间的语义关联；使用随机游走策略获得项目所属学科与专家研究兴趣共现关联的节点序列，并通过网络表示学习模型训练得到具有语义关联的项目所属学科与专家研究兴趣的向量表示；在此基础上，按照项目学科树层次结构逐层计算语义相似度，以实现多粒度的同行评议学术专长匹配。在爬取的知网和万方论文数据集、某专家评审数据集、以及百度百科词向量数据集上得到的实验结果表明，所提方法能提升项目所属学科与专家研究兴趣间的语义关联，并能有效应用于项目评审专家的学术专长匹配。

关键词: 专家推荐, 同行评议, 学术网络, 元路径, 表示学习

Abstract: Most of the existing expert recommendation processes rely on manual matching, which leads to the low accuracy of expert recommendation due to that they cannot fully capture the semantic association between the subject of the project and the interests of experts. To solve this problem, a matching method for academic expertise of project peer review experts was proposed. In the method, an academic network was constructed to establish the academic entity connection, and a meta-path was designed to capture the semantic association between different nodes in the academic network. By using the random walk strategy, the node sequence of co-occurrence association between the subject of the project and the expert research interests was obtained. And through the network representation learning model training, the vector representation with semantic association of the project subject and expert research interests was obtained. On this basis, the semantic similarity was calculated layer by layer according to the hierarchical structure of project subject tree to realize multi-granularity peer review academic expertise matching. Experimental results on the crawled datasets of HowNet and Wanfang papers, an expert review dataset and Baidu Baike word vector dataset show that this method can enhance the semantic association between the project subject and expert research interests, and can be effectively applied to the academic expertise matching of project review experts.

Key words: expert recommendation, peer review, academic network, meta-path, representation learning

中图分类号:

TP311

王梓森, 梁英, 刘政君, 谢小杰, 张伟, 史红周. 科研项目同行评议专家学术专长匹配方法[J]. 计算机应用, 2021, 41(8): 2418-2426.

WANG Zisen, LIANG Ying, LIU Zhengjun, XIE Xiaojie, ZHANG Wei, SHI Hongzhou. Matching method for academic expertise of research project peer review experts[J]. Journal of Computer Applications, 2021, 41(8): 2418-2426.

参考文献

[1] WU S,MANBER U. A fast algorithm for multi-pattern searching:TR-94-17[R]. Tucson,AZ:University of Arizona,1994:1-11.
[2] 张晔, 贾雨葶, 王新兵, 等. AceMap学术地图与AceKG学术知识图谱——学术数据可视化[J]. 上海交通大学学报,2018,52(10):1357-1362.(ZHANG Y,JIA Y T,WANG X B,et al. AceMap academic map and AceKG academic knowledge graph for academic data visualization[J]. Journal of Shanghai Jiao Tong University,2018,52(10):1357-1362.)
[3] VARELAS G, VOUTSAKIS E, RAFTOPOULOU P, et al. Semantic similarity methods in WordNet and their application to information retrieval on the web[C]//Proceedings of the 7th Annual ACM International Workshop on Web Information and Data Management. New York:ACM,2005:10-16.
[4] DONG Z D,DONG Q,HAO C L. HowNet and its computation of meaning[C]//Proceedings of the 23rd International Conference on Computational Linguistics:Demonstrations. Stroudsburg, PA:Association for Computational Linguistics,2010:53-56.
[5] DEERWESTER S,DUMAIS S T,FURNAS G W,et al. Indexing by latent semantic analysis[J]. Journal of the American Society for Information Science,1990,41(6):391-407.
[6] HOFMANN T. Unsupervised learning by probabilistic latent semantic analysis[J]. Machine Learning, 2001, 42(1/2):177-196.
[7] BLEI D M,NG A Y,JORDAN M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research,2003,3(1):993-1022.
[8] 彭云, 万常选, 江腾蛟, 等. 基于语义约束LDA的商品特征和情感词提取[J]. 软件学报,2017,28(3):676-693.(PENG Y, WAN C X,JIANG T J,et al. Extracting product aspects and user opinions based on semantic constrained LDA model[J]. Journal of Software,2017,28(3):676-693.)
[9] 何云, 李彤, 王炜, 等. 一种面向软件特征定位问题的语义相似度集成方法[J]. 计算机研究与发展,2019,56(2):394-409. (HE Y,LI T,WANG W,et al. A semantic similarity integration method for software feature location problem[J]. Journal of Computer Research and Development,2019,56(2):394-409.)
[10] 王伟, 黄德根. 基于滑动语义串匹配(SMOSS)的汉语词义消歧[J]. 小型微型计算机系统,2020,41(7):1345-1350.(WANG W,HUANG D G. Chinese word sense disambiguation based on Sliding Match Of Semantic String (SMOSS)[J]. Journal of Chinese Computer Systems,2020,41(7):1345-1350.)
[11] WANG C W,ZHOU T F,CHEN C,et al. HAM:a deep collaborative ranking method incorporating textual information[J]. Frontiers of Information Technology and Electronic Engineering, 2020,21(8):1206-1216.
[12] SCHLICHTKRULL M,KIPF T N,BLOEM P,et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the 2018 European Semantic Web Conference,LNCS 10843. Cham:Springer,2018:593-607.
[13] JI H Y,SHI C,WANG B. Attention based meta path fusion for heterogeneous information network embedding[C]//Proceedings of the 2018 Pacific Rim International Conference on Artificial Intelligence,LNCS 11012. Cham:Springer,2018:348-360.
[14] MIKOLOV T,CHEN K,CORRADO G,et al. Efficient estimation of word representations in vector space[EB/OL]. (2013-09-07)[2020-03-11]. https://arxiv.org/pdf/1301.3781.pdf.
[15] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2014:701-710.
[16] GROVER A,LESKOVEC J. node2vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2016:855-864.
[17] DONG Y X,CHAWLA N V,SWAMI A. metapath2vec:scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2017:135-144.
[18] 王文涛, 黄烨, 吴淋涛, 等. 基于改进随机游走的网络表示学习算法[J]. 计算机应用,2019,39(3):651-655.(WANG W T, HUANG Y,WU L T,et al. Network representation learning algorithm based on improved random walk[J]. Journal of Computer Applications,2019,39(3):651-655.)
[19] ZHANG W,LIANG Y,DONG X X. Representation learning in academic network based on research interest and meta-path[C]//Proceedings of the 2019 International Conference on Knowledge Science,Engineering and Management,LNCS 11776. Cham:Springer,2019:389-399.
[20] MIKOLOV T, SUTSKEVER I, KAI C, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2013:3111-3119.
[21] LI S,ZHAO Z,HU R F,et al. Analogical reasoning on Chinese morphological and semantic relations[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2018:138-143.

科研项目同行评议专家学术专长匹配方法

Matching method for academic expertise of research project peer review experts

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张萌, 李维华. 用户互动表示下的影响力最大化算法[J]. 计算机应用, 2021, 41(7): 1964-1969.
[2]	张蓉, 张献国. 基于层次异构图注意力网络的虚假评论检测[J]. 计算机应用, 2021, 41(5): 1275-1281.
[3]	林怿星, 唐华. 基于异构信息网络的混合推荐模型[J]. 计算机应用, 2021, 41(5): 1348-1355.
[4]	樊玮, 王慧敏, 邢艳. 基于自编码器的多视图属性网络表示学习模型[J]. 计算机应用, 2021, 41(4): 1064-1070.
[5]	郭景峰, 董慧, 张庭玮, 陈晓. 主题关注网络的表示学习[J]. 计算机应用, 2020, 40(2): 441-447.
[6]	张钊, 吉建民, 陈小平. 用于知识表示学习的对抗式负样本生成[J]. 计算机应用, 2019, 39(9): 2489-2493.
[7]	王文涛, 吴淋涛, 黄烨, 朱容波. 基于密集连接卷积神经网络的链路预测模型[J]. 计算机应用, 2019, 39(6): 1632-1638.
[8]	刘正铭, 马宏, 刘树新, 李海涛, 常圣. 融合节点描述属性信息的网络表示学习算法[J]. 计算机应用, 2019, 39(4): 1012-1020.
[9]	王文涛, 黄烨, 吴淋涛, 柯璇, 唐菀. 基于改进随机游走的网络表示学习算法[J]. 计算机应用, 2019, 39(3): 651-655.
[10]	陈婉杰, 盛益强. 基于网络表示学习的非单一维度的社区发现算法[J]. 计算机应用, 2019, 39(12): 3467-3475.
[11]	徐红艳, 王丹, 王富海, 王嵘冰. 融合潜在狄利克雷分布与元路径分析的用户相关性度量方法[J]. 计算机应用, 2019, 39(11): 3288-3292.
[12]	邱庆羽, 李婧, 全兵, 童超, 张利君, 张海仙. 基于文献信息网络语义特征的相似性搜索[J]. 计算机应用, 2018, 38(5): 1327-1333.
[13]	刘雨心, 王莉, 张昊. 基于分层注意力机制的神经网络垃圾评论检测模型[J]. 计算机应用, 2018, 38(11): 3063-3068.
[14]	刘思, 刘海, 陈启买, 贺超波. 基于网络表示学习与随机游走的链路预测算法[J]. 计算机应用, 2017, 37(8): 2234-2239.
[15]	李岩, 张博文, 郝红卫. 基于语义向量表示的查询扩展方法[J]. 计算机应用, 2016, 36(9): 2526-2530.